Borrowing it
Nothing to install: this file belongs to TikiTribe/claude-secure-coding-rules. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/TikiTribe/claude-secure-coding-rules/main/CLAUDE.mdgit clone --depth 1 https://github.com/TikiTribe/claude-secure-coding-rulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/instructions/tikitribe/claude-secure-coding-rules/claude-md)<a href="https://agentmods.dev/instructions/tikitribe/claude-secure-coding-rules/claude-md"><img src="https://agentmods.dev/badge/instructions/tikitribe/claude-secure-coding-rules/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/tikitribe/claude-secure-coding-rules/claude-md"><img src="https://agentmods.dev/badge/instructions/tikitribe/claude-secure-coding-rules/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.02599 | $0.02599 |
| Opus 5.5 | $0.01040 | $0.01040 |
| Sonnet 5.5 | $0.00520 | $0.00520 |
| Haiku 4.5 | $0.00260 | $0.00260 |
Grade A, and why
claude-secure-coding-rules CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md - Secure Coding Rules for Claude Code
This repository provides comprehensive security rules for Claude Code, covering web applications, AI/ML systems, and agentic AI.
Project Overview
Purpose: Open-source security rules that guide Claude Code to generate secure code by default
Coverage:
- OWASP Top 10 2025 (web application security)
- OWASP MCP Top 10 2025 (Model Context Protocol security)
- AI/ML security (NIST AI RMF, MITRE ATLAS, Google SAIF)
- Agentic AI security (tool use, autonomy, sandboxing)
- Language-specific rules (Python, JavaScript, TypeScript, Go, Rust, Java, C#, Ruby, R, C++, Julia, SQL)
- Backend frameworks (FastAPI, Express, Django, Flask, NestJS)
- AI/ML frameworks (LangChain, CrewAI, AutoGen, Transformers, vLLM, Triton, TorchServe, Ray Serve, BentoML, MLflow, Modal)
- Frontend frameworks (React, Next.js, Vue, Angular, Svelte)
Repository Structure
claude-secure-coding-rules/
├── rules/
│ ├── _core/ # Foundation rules (apply to all projects)
│ │ ├── owasp-2025.md # OWASP Top 10 2025 security rules
│ │ ├── mcp-security.md # Model Context Protocol (MCP) security rules
│ │ ├── ai-security.md # AI/ML system security rules
│ │ └── agent-security.md # Agentic AI security rules
│ │
│ ├── languages/ # Language-specific security rules
│ │ ├── python/CLAUDE.md # Deserialization, subprocess, path traversal, crypto, SQL
│ │ ├── javascript/CLAUDE.md # eval, prototype pollution, DOM security, Node.js
│ │ ├── typescript/CLAUDE.md # Type safety, validation, any types
│ │ ├── go/CLAUDE.md # Concurrency, context, templates, error handling
│ │ ├── rust/CLAUDE.md # unsafe blocks, FFI, memory safety, crypto
│ │ ├── java/CLAUDE.md # Serialization, JNDI, reflection, streams
│ │ ├── csharp/CLAUDE.md # .NET patterns, LINQ injection, assemblies
│ │ ├── ruby/CLAUDE.md # Metaprogramming, ERB, mass assignment
│ │ ├── r/CLAUDE.md # Shiny apps, data security, package verification
│ │ ├── cpp/CLAUDE.md # Memory safety, buffer overflows, smart pointers
│ │ ├── julia/CLAUDE.md # Metaprogramming, type safety, serialization
│ │ └── sql/CLAUDE.md # Injection, permissions, stored procedures
│ │
│ ├── backend/ # Backend framework rules
│ │ ├── fastapi/CLAUDE.md # Pydantic validation, JWT, authorization, CORS, AI APIs
│ │ ├── express/CLAUDE.md # Helmet, sessions, rate limiting, file uploads
│ │ ├── django/CLAUDE.md # ORM, CSRF, templates, settings
│ │ ├── flask/CLAUDE.md # Werkzeug, sessions, blueprints, extensions
│ │ ├── nestjs/CLAUDE.md # Decorators, guards, pipes, interceptors
│ │ ├── langchain/CLAUDE.md # Prompt injection, tool security, chains, RAG
│ │ ├── crewai/CLAUDE.md # Multi-agent trust, delegation, memory isolation
│ │ ├── autogen/CLAUDE.md # Code execution, human-in-loop, sandboxing
│ │ ├── transformers/CLAUDE.md # Model loading, tokenizers, fine-tuning
│ │ ├── vllm/CLAUDE.md # KV cache, PagedAttention, batching security
│ │ ├── triton/CLAUDE.md # GPU isolation, ensemble security, gRPC
│ │ ├── torchserve/CLAUDE.md # MAR files, custom handlers, management API
│ │ ├── ray-serve/CLAUDE.md # Deployment, autoscaling, serialization
│ │ ├── bentoml/CLAUDE.md # Bento packaging, runners, API security
│ │ ├── mlflow/CLAUDE.md # Model registry, experiment tracking, artifacts
│ │ └── modal/CLAUDE.md # Serverless functions, secrets, containers
│ │
│ └── frontend/ # Frontend framework rules
│ ├── react/CLAUDE.md # XSS prevention, state management, CSRF, forms
│ ├── nextjs/CLAUDE.md # Server Components, Server Actions, middleware, env vars
│ ├── vue/CLAUDE.md # v-html, computed properties, Vuex, router guards
│ ├── angular/CLAUDE.md # DomSanitizer, template injection, HTTP client
│ └── svelte/CLAUDE.md # {@html}, stores, SSR, form actions
│
│ ├── containers/ # Container security rules
│ │ ├── _core/container-security.md # Core container principles
│ │ ├── docker/CLAUDE.md # Docker (images, runtime, scanning, dependencies)
│ │ ├── kubernetes/CLAUDE.md # Kubernetes (PSS, RBAC, NetworkPolicies, supply chain)
│ │ └── helm/CLAUDE.md # Helm (secrets, security context, schema, provenance)
│ │
│ ├── iac/ # Infrastructure as Code rules
│ │ ├── _core/iac-security.md # Core IaC security principles
│ │ ├── terraform/CLAUDE.md # Terraform (state, modules, providers)
│ │ └── pulumi/CLAUDE.md # Pulumi (secrets, CrossGuard, ESC)
│ │
│ └── cicd/ # CI/CD security rules
│ ├── _core/cicd-security.md # Core CI/CD principles
│ ├── github-actions/CLAUDE.md # GitHub Actions (SHA pinning, OIDC)
│ └── gitlab-ci/CLAUDE.md # GitLab CI (protected vars, scanning)
│
├── templates/ # Templates for adding new rules
│ ├── rule-template.md # Template for individual rules
│ └── framework-template.md # Template for framework rule sets
│
├── docs/ # Documentation and guides
│ └── CONTRIBUTING.md # Contribution guidelines with quality standards
│
├── compliance/ # Compliance mapping (future)
│
├── CLAUDE.md # This file - project instructions
├── README.md # User documentation and implementation guide
└── LICENSE # MIT License
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 215 lines · 2,599 tokens per session scan A 4e88185726e5
claude-secure-coding-rules CLAUDE.md is an instructions file published in the GitHub repository TikiTribe/claude-secure-coding-rules (143 stars, last pushed 5mo ago), licensed MIT. It adds 2,599 tokens to every session, about $0.0104 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.